New research, presented at the ANESTHESIOLOGY 2020 annual meeting, has suggested that artificial intelligence (AI) can predict patients who are at the highest risk for severe pain after surgery, which could help determine which patients would most benefit from personalized pain treatment that uses non-opioid alternatives.

Many patients who experience severe pain after surgery are advised higher doses of opioids for a longer duration, which could further increase their risk for opioid abuse disorder.

If doctors know which patients are at higher risk for severe pain after surgery, they can create a treatment plan using non-opioid alternatives, such as epidurals, nerve blocks, and other medications, to effectively manage pain and reduce the need for opioid drugs.

Currently, doctors use a long list of questionnaires to identify patients at higher risk for severe pain after surgery by asking about their anxiety, sleep, and depression.

However, the new study has sought a faster and more effective way of identifying patients with severe post-surgery pain using AI using three machine learning models that analyze patients’ electronic medical records (EMRs).

Doctors can use this tool to identify your age, body mass index, gender, pre-existing pain, and prior opioid use.

Lead author Dr. Mieke Soens said, “We plan to integrate the models with our electronic medical records to provide a prediction of post-surgical pain for each patient.”

“If the patient is determined to be at high risk for severe post-surgical pain, the physician anesthesiologist can then adjust the patient’s anesthesia plan to maximize non-opioid pain management strategies that would reduce the need for opioids after surgery,” she added.

The study researchers looked at data from more than 5,900 patients who had a wide variety of surgeries. Of those, more than 20% of the patients consumed 90 mg morphine after surgery.

The researchers looked at more than 160 potential factors to predict severe post-surgical pain based on EMRs and consultations with doctors. They then created AI models that looked at EMRs and segregated those 160 factors. The models accurately predicted patients’ tendency of severe pain after surgery and their potential opioid needs.

Dr. Soens said, “Electronic medical records are a valuable and underused source of patient data and can be employed effectively to enhance patients’ lives.” “Selectively identifying patients who typically need high doses of opioids after surgery is important to help reduce opioid misuse,” she added.